4 papers with code • 1 benchmarks • 1 datasets


Most implemented papers

Gated Graph Sequence Neural Networks

dmlc/dgl 17 Nov 2015

Graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases.

Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks

IBM/Graph2Seq ICLR 2019

Our method first generates the node and graph embeddings using an improved graph-based neural network with a novel aggregation strategy to incorporate edge direction information in the node embeddings.

SQL-to-Text Generation with Graph-to-Sequence Model

IBM/SQL-to-Text EMNLP 2018

Previous work approaches the SQL-to-text generation task using vanilla Seq2Seq models, which may not fully capture the inherent graph-structured information in SQL query.

Augmenting Multi-Turn Text-to-SQL Datasets with Self-Play

leuchine/self_play_picard 21 Oct 2022

We first design a SQL-to-text model conditioned on a sampled goal query, which represents a user's intent, that then converses with a text-to-SQL semantic parser to generate new interactions.